Natural Language Reasoning, A Survey
Abstract
This survey paper proposes a clearer view of natural language reasoning in the field of Natural Language Processing (NLP), both conceptually and practically. Conceptually, we provide a distinct definition for natural language reasoning in NLP, based on both philosophy and NLP scenarios, discuss what types of tasks require reasoning, and introduce a taxonomy of reasoning. Practically, we conduct a comprehensive literature review on natural language reasoning in NLP, mainly covering classical logical reasoning, natural language inference, multi-hop question answering, and commonsense reasoning. The paper also identifies and views backward reasoning, a powerful paradigm for multi-step reasoning, and introduces defeasible reasoning as one of the most important future directions in natural language reasoning research. We focus on single-modality unstructured natural language text, excluding neuro-symbolic techniques and mathematical reasoning.
Cite
@article{arxiv.2303.14725,
title = {Natural Language Reasoning, A Survey},
author = {Fei Yu and Hongbo Zhang and Prayag Tiwari and Benyou Wang},
journal= {arXiv preprint arXiv:2303.14725},
year = {2023}
}
Comments
https://github.com/FreedomIntelligence/ReasoningNLP